mptcp: push pending frames when subflow has free space

When multiple subflows are active, we can receive a
window update on subflow with no write space available.
MPTCP will try to push frames on such subflow and will
fail. Pending frames will be pushed only after receiving
a window update on a subflow with some wspace available.

Overall the above could lead to suboptimal aggregate
bandwidth usage.

Instead, we should try to push pending frames as soon as
the subflow reaches both conditions mentioned above.

We can finally enable self-tests with asymmetric links,
as the above makes them finally pass.

Fixes: 6f8a612a33e4 ("mptcp: keep track of advertised windows right edge")
Reviewed-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index e8a1adf299d8941eeddb4aefb6499a3c73743aae..e0d21c0607e5397f620c31ca8f2e10cb1d03a50c 100644 (file)
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -875,10 +875,13 @@ static void ack_update_msk(struct mptcp_sock *msk,
 
        new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
 
-       if (after64(new_wnd_end, msk->wnd_end)) {
+       if (after64(new_wnd_end, msk->wnd_end))
                msk->wnd_end = new_wnd_end;
-               __mptcp_wnd_updated(sk, ssk);
-       }
+
+       /* this assumes mptcp_incoming_options() is invoked after tcp_ack() */
+       if (after64(msk->wnd_end, READ_ONCE(msk->snd_nxt)) &&
+           sk_stream_memory_free(ssk))
+               __mptcp_check_push(sk, ssk);
 
        if (after64(new_snd_una, old_snd_una)) {
                msk->snd_una = new_snd_una;
@@ -944,8 +947,8 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
                 * helpers are cheap.
                 */
                mptcp_data_lock(subflow->conn);
-               if (mptcp_send_head(subflow->conn))
-                       __mptcp_wnd_updated(subflow->conn, sk);
+               if (sk_stream_memory_free(sk))
+                       __mptcp_check_push(subflow->conn, sk);
                __mptcp_data_acked(subflow->conn);
                mptcp_data_unlock(subflow->conn);
                return;

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 64c0c54c80e80d62cf893e6ef729772af563a5af..b53a91801a6c64ed09ea321839e29976ac20db2d 100644 (file)
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2915,7 +2915,7 @@ void __mptcp_data_acked(struct sock *sk)
                mptcp_schedule_work(sk);
 }
 
-void __mptcp_wnd_updated(struct sock *sk, struct sock *ssk)
+void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 {
        if (!mptcp_send_head(sk))
                return;

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 7cf9d110b85f3124c311b33bebc993c2351eac37..d67de793d363f6e041fd0aabffb7d35bf4930952 100644 (file)
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -503,7 +503,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk);
 void mptcp_data_ready(struct sock *sk, struct sock *ssk);
 bool mptcp_finish_join(struct sock *sk);
 bool mptcp_schedule_work(struct sock *sk);
-void __mptcp_wnd_updated(struct sock *sk, struct sock *ssk);
+void __mptcp_check_push(struct sock *sk, struct sock *ssk);
 void __mptcp_data_acked(struct sock *sk);
 void mptcp_subflow_eof(struct sock *sk);
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);

diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 2f649b431456a22c4ed59c61176548c6b915f8b8..f039ee57eb3c79b4d6c08ba07e8c1b8f2b9e6228 100755 (executable)
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -287,7 +287,7 @@ run_test 10 10 0 0 "balanced bwidth"
 run_test 10 10 1 50 "balanced bwidth with unbalanced delay"
 
 # we still need some additional infrastructure to pass the following test-cases
-# run_test 30 10 0 0 "unbalanced bwidth"
-# run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay"
-# run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay"
+run_test 30 10 0 0 "unbalanced bwidth"
+run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay"
+run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay"
 exit $ret